# Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network

arXiv: https://arxiv.org/abs/1703.09695 · HTML: https://mlsanity.com/paper/1703.09695/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2017.

## Built on by (most cited first, 11 of 11)

- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [Uncertainty-aware Joint Salient Object and Camouflaged Object Detection](https://mlsanity.com/paper/2104.02628/) (2021)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [Towards Deeper Understanding of Camouflaged Object Detection](https://mlsanity.com/paper/2205.11333/) (2022)
- [AI-Generated Images as Data Source: The Dawn of Synthetic Era](https://mlsanity.com/paper/2310.01830/) (2023)
- [Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary](https://mlsanity.com/paper/2110.01519/) (2021)
- [Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation](https://mlsanity.com/paper/2410.19836/) (2024)
- [Transferable Attack for Semantic Segmentation](https://mlsanity.com/paper/2307.16572/) (2023)
- [A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features](https://mlsanity.com/paper/2105.00967/) (2021)
- [One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model](https://mlsanity.com/paper/2205.01233/) (2022)
- [R2S100K: Road-Region Segmentation Dataset For Semi-Supervised Autonomous Driving in the Wild](https://mlsanity.com/paper/2308.06393/) (2023)

## Abstract (arXiv)

Semantic segmentation has been a long standing challenging task in computer vision. It aims at assigning a label to each image pixel and needs significant number of pixellevel annotated data, which is often unavailable. To address this lack, in this paper, we leverage, on one hand, massive amount of available unlabeled or weakly labeled data, and on the other hand, non-real images created through Generative Adversarial Networks. In particular, we propose a semi-supervised framework ,based on Generative Adversarial Networks (GANs), which consists of a generator network to provide extra training examples to a multi-class classifier, acting as discriminator in the GAN framework, that assigns sample a label y from the K possible classes or marks it as a fake sample (extra class). The underlying idea is that adding large fake visual data forces real samples to be close in the feature space, enabling a bottom-up clustering process, which, in turn, improves multiclass pixel classification. To ensure higher quality of generated images for GANs with consequent improved pixel classification, we extend the above framework by adding weakly annotated data, i.e., we provide class level information to the generator. We tested our approaches on several challenging benchmarking visual datasets, i.e. PASCAL, SiftFLow, Stanford and CamVid, achieving competitive performance also compared to state-of-the-art semantic segmentation method